FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963670239> ?p ?o ?g. }

• W2963670239 abstract "Weakly supervised semantic segmentation and localization have a problem of focusing only on the most important parts of an image since they use only image-level annotations. In this paper, we solve this problem fundamentally via two-phase learning. Our networks are trained in two steps. In the first step, a conventional fully convolutional network (FCN) is trained to find the most discriminative parts of an image. In the second step, the activations on the most salient parts are suppressed by inference conditional feedback, and then the second learning is performed to find the area of the next most important parts. By combining the activations of both phases, the entire portion of the target object can be captured. Our proposed training scheme is novel and can be utilized in well-designed techniques for weakly supervised semantic segmentation, salient region detection, and object location prediction. Detailed experiments demonstrate the effectiveness of our two-phase learning in each task." @default.
• W2963670239 created "2019-07-30" @default.
• W2963670239 creator A5016424347 @default.
• W2963670239 creator A5063965796 @default.
• W2963670239 creator A5084688455 @default.
• W2963670239 date "2017-10-01" @default.
• W2963670239 modified "2023-10-16" @default.
• W2963670239 title "Two-Phase Learning for Weakly Supervised Object Localization" @default.
• W2963670239 cites W1536680647 @default.
• W2963670239 cites W1745334888 @default.
• W2963670239 cites W1783315696 @default.
• W2963670239 cites W1903029394 @default.
• W2963670239 cites W1934621328 @default.
• W2963670239 cites W1945608308 @default.
• W2963670239 cites W1991367009 @default.
• W2963670239 cites W1993433125 @default.
• W2963670239 cites W1994488211 @default.
• W2963670239 cites W2010181071 @default.
• W2963670239 cites W2029731618 @default.
• W2963670239 cites W2031489346 @default.
• W2963670239 cites W2046382188 @default.
• W2963670239 cites W2066624635 @default.
• W2963670239 cites W2088049833 @default.
• W2963670239 cites W2102605133 @default.
• W2963670239 cites W2109326754 @default.
• W2963670239 cites W2127194945 @default.
• W2963670239 cites W2133324800 @default.
• W2963670239 cites W2133515615 @default.
• W2963670239 cites W2141197099 @default.
• W2963670239 cites W2141739106 @default.
• W2963670239 cites W2144794286 @default.
• W2963670239 cites W2161185676 @default.
• W2963670239 cites W2221898772 @default.
• W2963670239 cites W2306289963 @default.
• W2963670239 cites W2442791716 @default.
• W2963670239 cites W2496066288 @default.
• W2963670239 cites W2503388974 @default.
• W2963670239 cites W2516803306 @default.
• W2963670239 cites W2517617019 @default.
• W2963670239 cites W2520746254 @default.
• W2963670239 cites W2963064675 @default.
• W2963670239 cites W2963537460 @default.
• W2963670239 cites W2963603913 @default.
• W2963670239 cites W611457968 @default.
• W2963670239 doi "https://doi.org/10.1109/iccv.2017.382" @default.
• W2963670239 hasPublicationYear "2017" @default.
• W2963670239 type Work @default.
• W2963670239 sameAs 2963670239 @default.
• W2963670239 citedByCount "106" @default.
• W2963670239 countsByYear W29636702392018 @default.
• W2963670239 countsByYear W29636702392019 @default.
• W2963670239 countsByYear W29636702392020 @default.
• W2963670239 countsByYear W29636702392021 @default.
• W2963670239 countsByYear W29636702392022 @default.
• W2963670239 countsByYear W29636702392023 @default.
• W2963670239 crossrefType "proceedings-article" @default.
• W2963670239 hasAuthorship W2963670239A5016424347 @default.
• W2963670239 hasAuthorship W2963670239A5063965796 @default.
• W2963670239 hasAuthorship W2963670239A5084688455 @default.
• W2963670239 hasBestOaLocation W29636702392 @default.
• W2963670239 hasConcept C115961682 @default.
• W2963670239 hasConcept C119857082 @default.
• W2963670239 hasConcept C124504099 @default.
• W2963670239 hasConcept C136389625 @default.
• W2963670239 hasConcept C153180895 @default.
• W2963670239 hasConcept C154945302 @default.
• W2963670239 hasConcept C162324750 @default.
• W2963670239 hasConcept C187736073 @default.
• W2963670239 hasConcept C2776151529 @default.
• W2963670239 hasConcept C2776214188 @default.
• W2963670239 hasConcept C2780451532 @default.
• W2963670239 hasConcept C2780719617 @default.
• W2963670239 hasConcept C2781238097 @default.
• W2963670239 hasConcept C31972630 @default.
• W2963670239 hasConcept C41008148 @default.
• W2963670239 hasConcept C50644808 @default.
• W2963670239 hasConcept C81363708 @default.
• W2963670239 hasConcept C89600930 @default.
• W2963670239 hasConcept C97931131 @default.
• W2963670239 hasConceptScore W2963670239C115961682 @default.
• W2963670239 hasConceptScore W2963670239C119857082 @default.
• W2963670239 hasConceptScore W2963670239C124504099 @default.
• W2963670239 hasConceptScore W2963670239C136389625 @default.
• W2963670239 hasConceptScore W2963670239C153180895 @default.
• W2963670239 hasConceptScore W2963670239C154945302 @default.
• W2963670239 hasConceptScore W2963670239C162324750 @default.
• W2963670239 hasConceptScore W2963670239C187736073 @default.
• W2963670239 hasConceptScore W2963670239C2776151529 @default.
• W2963670239 hasConceptScore W2963670239C2776214188 @default.
• W2963670239 hasConceptScore W2963670239C2780451532 @default.
• W2963670239 hasConceptScore W2963670239C2780719617 @default.
• W2963670239 hasConceptScore W2963670239C2781238097 @default.
• W2963670239 hasConceptScore W2963670239C31972630 @default.
• W2963670239 hasConceptScore W2963670239C41008148 @default.
• W2963670239 hasConceptScore W2963670239C50644808 @default.
• W2963670239 hasConceptScore W2963670239C81363708 @default.
• W2963670239 hasConceptScore W2963670239C89600930 @default.
• W2963670239 hasConceptScore W2963670239C97931131 @default.
• W2963670239 hasLocation W29636702391 @default.
• W2963670239 hasLocation W29636702392 @default.

• next